Merge pull request #117 from Portkey-AI/feat/models-openapi

feat: add model pricing endpoint and related schemas

Author: vrushankportkey

openapi.yaml

@@ -23,6 +23,10 @@ x-server-groups:
     - url: SELF_HOSTED_GATEWAY_URL
       description: Self-Hosted Gateway URL
 
+  PublicServers: &PublicServers
+    - url: https://api.portkey.ai
+      description: Portkey Public API (no auth required)
+
 x-mint:
   mcp:
     enabled: true
@@ -110,6 +114,8 @@ tags:
     description: Manage usage limits policies to control total usage over time
   - name: Rate Limits Policies
     description: Manage rate limits policies to control request or token rates
+  - name: Model Pricing
+    description: Model pricing configurations for 2300+ LLMs across 40+ providers
 
 
 paths:
@@ -19425,6 +19431,165 @@ paths:
                   - object
                   - data
 
+  /model-configs/pricing/{provider}/{model}:
+    servers: *PublicServers
+    get:
+      summary: Get Model Pricing
+      security: []
+      description: |
+        Returns pricing configuration for a specific model.
+        
+        **Note:** Prices are in USD cents per token.
+        
+        ## Supported Providers
+        
+        openai, anthropic, google, azure-openai, bedrock, mistral-ai, cohere, 
+        together-ai, groq, deepseek, fireworks-ai, perplexity-ai, anyscale, 
+        deepinfra, cerebras, x-ai, and 25+ more.
+        
+        ## Example Response Fields
+        
+        | Field | Description | Unit |
+        |-------|-------------|------|
+        | `request_token.price` | Input token cost | cents/token |
+        | `response_token.price` | Output token cost | cents/token |
+        | `cache_write_input_token.price` | Cache write cost | cents/token |
+        | `cache_read_input_token.price` | Cache read cost | cents/token |
+        | `additional_units.*` | Provider-specific features | cents/unit |
+        
+      operationId: getModelPricing
+      tags:
+        - Model Pricing
+      parameters:
+        - name: provider
+          in: path
+          required: true
+          description: |
+            Provider identifier. Use lowercase with hyphens.
+            
+            Examples: `openai`, `anthropic`, `google`, `azure-openai`, `bedrock`, `x-ai`
+          schema:
+            type: string
+            example: openai
+        - name: model
+          in: path
+          required: true
+          description: |
+            Model identifier. Use the exact model name as specified by the provider.
+            
+            Examples: `gpt-5`, `gpt-5.2`, `claude-opus-4-5-20251101`, `gemini-3.0-pro`
+          schema:
+            type: string
+            example: gpt-5
+      responses:
+        '200':
+          description: Pricing configuration for the specified model
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ModelPricingConfig'
+              examples:
+                openai-gpt4:
+                  summary: OpenAI GPT-4
+                  value:
+                    pay_as_you_go:
+                      request_token:
+                        price: 0.003
+                      response_token:
+                        price: 0.006
+                    calculate:
+                      request:
+                        operation: sum
+                        operands:
+                          - operation: multiply
+                            operands:
+                              - value: input_tokens
+                              - value: rates.request_token
+                          - operation: multiply
+                            operands:
+                              - value: cache_write_tokens
+                              - value: rates.cache_write_input_token
+                          - operation: multiply
+                            operands:
+                              - value: cache_read_tokens
+                              - value: rates.cache_read_input_token
+                      response:
+                        operation: multiply
+                        operands:
+                          - value: output_tokens
+                          - value: rates.response_token
+                    currency: USD
+                openai-gpt4o-with-tools:
+                  summary: OpenAI GPT-4o (with additional units)
+                  value:
+                    pay_as_you_go:
+                      request_token:
+                        price: 0.00025
+                      response_token:
+                        price: 0.001
+                      cache_write_input_token:
+                        price: 0
+                      cache_read_input_token:
+                        price: 0.000125
+                      additional_units:
+                        web_search:
+                          price: 1
+                        file_search:
+                          price: 0.25
+                    calculate:
+                      request:
+                        operation: sum
+                        operands:
+                          - operation: multiply
+                            operands:
+                              - value: input_tokens
+                              - value: rates.request_token
+                      response:
+                        operation: multiply
+                        operands:
+                          - value: output_tokens
+                          - value: rates.response_token
+                    currency: USD
+                anthropic-claude:
+                  summary: Anthropic Claude 3.5 Sonnet
+                  value:
+                    pay_as_you_go:
+                      request_token:
+                        price: 0.0003
+                      response_token:
+                        price: 0.0015
+                      cache_read_input_token:
+                        price: 0.00003
+                      cache_write_input_token:
+                        price: 0.000375
+                    currency: USD
+                google-gemini:
+                  summary: Google Gemini 2.5 Pro (with thinking tokens)
+                  value:
+                    pay_as_you_go:
+                      request_token:
+                        price: 0.000125
+                      response_token:
+                        price: 0.001
+                      additional_units:
+                        thinking_token:
+                          price: 0.001
+                        web_search:
+                          price: 3.5
+                        search:
+                          price: 3.5
+                    currency: USD
+        '404':
+          description: Model or provider not found
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    example: Model not found
+
 
 components:
   securitySchemes:
@@ -19711,6 +19876,133 @@ components:
         type: string
 
   schemas:
+    ModelPricingConfig:
+      type: object
+      description: Complete pricing configuration for a model
+      properties:
+        pay_as_you_go:
+          $ref: '#/components/schemas/ModelPayAsYouGo'
+        calculate:
+          $ref: '#/components/schemas/ModelCalculateConfig'
+        currency:
+          type: string
+          enum: [USD]
+          description: Currency code (always USD)
+        finetune_config:
+          $ref: '#/components/schemas/ModelFinetuneConfig'
+
+    ModelPayAsYouGo:
+      type: object
+      description: Token-based pricing (all prices in USD cents)
+      properties:
+        request_token:
+          $ref: '#/components/schemas/ModelTokenPrice'
+        response_token:
+          $ref: '#/components/schemas/ModelTokenPrice'
+        cache_write_input_token:
+          $ref: '#/components/schemas/ModelTokenPrice'
+        cache_read_input_token:
+          $ref: '#/components/schemas/ModelTokenPrice'
+        request_audio_token:
+          $ref: '#/components/schemas/ModelTokenPrice'
+        response_audio_token:
+          $ref: '#/components/schemas/ModelTokenPrice'
+        cache_read_audio_input_token:
+          $ref: '#/components/schemas/ModelTokenPrice'
+        additional_units:
+          type: object
+          description: |
+            Provider-specific additional pricing units.
+            
+            Common additional units:
+            - `web_search`: Web search tool usage
+            - `file_search`: File search tool usage
+            - `thinking_token`: Chain-of-thought reasoning tokens (Google)
+            - `image_token`: Image generation tokens
+            - `video_duration_seconds_*`: Video generation (OpenAI Sora)
+          additionalProperties:
+            $ref: '#/components/schemas/ModelTokenPrice'
+        image:
+          $ref: '#/components/schemas/ModelImagePricing'
+
+    ModelTokenPrice:
+      type: object
+      description: Price object (value is in USD cents)
+      properties:
+        price:
+          type: number
+          description: |
+            Price in USD cents per token/unit.
+            
+            Example: `0.003` = 0.003 cents/token = $0.03 per 1K tokens
+
+    ModelImagePricing:
+      type: object
+      description: Image generation pricing by quality and size
+      additionalProperties:
+        type: object
+        additionalProperties:
+          $ref: '#/components/schemas/ModelTokenPrice'
+      example:
+        standard:
+          1024x1024:
+            price: 4
+          1024x1792:
+            price: 8
+        hd:
+          1024x1024:
+            price: 8
+          1024x1792:
+            price: 12
+
+    ModelCalculateConfig:
+      type: object
+      description: Cost calculation formulas
+      properties:
+        request:
+          $ref: '#/components/schemas/ModelCalculateOperation'
+        response:
+          $ref: '#/components/schemas/ModelCalculateOperation'
+
+    ModelCalculateOperation:
+      type: object
+      description: Mathematical operation for cost calculation
+      properties:
+        operation:
+          type: string
+          enum: [sum, multiply]
+          description: Operation type
+        operands:
+          type: array
+          description: Operands for the operation
+          items:
+            oneOf:
+              - $ref: '#/components/schemas/ModelCalculateOperation'
+              - $ref: '#/components/schemas/ModelValueReference'
+
+    ModelValueReference:
+      type: object
+      properties:
+        value:
+          type: string
+          description: |
+            Reference to a value or rate.
+            
+            Examples:
+            - `input_tokens`: Number of input tokens
+            - `output_tokens`: Number of output tokens
+            - `rates.request_token`: Request token rate
+            - `rates.response_token`: Response token rate
+
+    ModelFinetuneConfig:
+      type: object
+      description: Fine-tuning pricing configuration
+      properties:
+        pay_per_token:
+          $ref: '#/components/schemas/ModelTokenPrice'
+        pay_per_hour:
+          $ref: '#/components/schemas/ModelTokenPrice'
+
     Error:
       type: object
       properties: